A design-system workflow for FramingUI projects, which are projects that use shared visual rules such as colors, spacing, themes, icons, and reusable interface parts.

Use it when building or restyling FramingUI screens, pages, layouts, components, or themes, or when writing or reviewing the project's layout contract.

It gives coding agents a defined way to build or review screens so the result follows the project's existing design system instead of inventing inconsistent styles.

framingui — Skill for Claude Code and Codex by soo-kate

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add soo-kate/framingui-skill --skill framingui

Clone the repo

git clone --depth 1 https://github.com/soo-kate/framingui-skill

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/soo-kate/framingui-skill/framingui/github.svg)](https://agentmods.dev/skills/soo-kate/framingui-skill/framingui)

Your own site

<a href="https://agentmods.dev/skills/soo-kate/framingui-skill/framingui"><img src="https://agentmods.dev/badge/skills/soo-kate/framingui-skill/framingui/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/soo-kate/framingui-skill/framingui"><img src="https://agentmods.dev/badge/skills/soo-kate/framingui-skill/framingui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,450 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00098	$0.03450
Opus 5	$0.00049	$0.01725
Sonnet 5	$0.00020	$0.00690
Haiku 4.5	$0.00010	$0.00345

Measured 10d ago against content hash 893abfd851df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

framingui scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/doctor.mjs, scripts/generate-screen.mjs, scripts/layout.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

mcp/skill/framingui/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FramingUI Screen Workflow (free profile)

FramingUI is a token-driven design system. This is the free profile: 1 free theme (OKLCH tokens + ready-made Tailwind "recipe" class strings + pre-generated --fui-* CSS custom properties) plus 9 licensed themes listed as a catalog only, a 20-component screen contract inside 30 free components, 34 licensed components (real, catalog-listed, not shipped here), layout tokens (12 shells / 8 pages / 17 section patterns — named in references/tokens.md, translated into markup in references/layout.md), 3 icon libraries, and 9 screen recipes — machine-checkable grammars for what a screen of a given job must contain (references/recipes.md). Your job is to compose screens FROM this system, never around it. P0-D makes the final artifact source-first: an AgenticLayoutContract points at direct JSX/TSX and a CSS Module; the legacy screen generator is only a scaffold/migration helper.

Themes render through a scope boundary, not a provider-wraps-tree pattern: mount <FramingUIScope theme="<themeId>" scopeId="app">...</FramingUIScope> from @framingui/ui around the app root, and load the theme's pre-generated CSS (assets/themes/css/<id>.css) into the page. The scope stamps [data-fui-scope][data-fui-theme="<id>"] on its root element, which is exactly what that CSS's selectors target to define the --fui-* custom properties — Tailwind recipe classes and any hand-written CSS both read from those variables. Without both the scope markup AND the theme CSS actually loaded, nothing renders wrong loudly — it silently falls back to the default palette.

When NOT to use: projects that don't use FramingUI; backend/API work; native mobile screens (this skill covers the web path).

Everything is local. No server, no accounts, no telemetry. Data lives in assets/, docs in references/, tools in scripts/ (plain node, zero install). This folder works unchanged in Claude Code (.claude/skills/) and OpenAI Codex (.agents/skills/) — install paths are in INSTALL.md.

Read the full file on GitHub · 180 lines

Files

What ships with it

28 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 180 lines · 98 tokens per session scan A 893abfd851df

Subscribe to this mod's changes

framingui is a skill published in the GitHub repository soo-kate/framingui-skill (4 stars, last pushed 18d ago), licensed MIT. It adds 98 tokens to every session and 3,450 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Design and UX

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

framingui